153 datasets found

The dataset used in the paper is a large-scale recommendation system dataset, where each item or user may correspond to a separate bandit arm.

The dataset used in the paper is a quantized neural network model implemented in OpenVINO, which is a framework for deploying neural networks on embedded and Edge devices.

The authors used four real-world datasets: MNIST, Yelp, MovieLens, and Disin.

The dataset used in this paper is a set of real neural network bugs collected from stackoverflow, including dimension errors, input shape bugs, and argument errors.

The dataset used in this paper is a set of randomly generated neural networks with bugs, including dimension errors, input shape bugs, and argument errors.

The dataset used in the paper is a SISO model of the fast processes in a PWR. The dataset is created using the dNEAT algorithm, which is an evolutionary algorithm that optimizes...

The dataset used in the paper is a black-box model of a dynamic system with time delays. The dataset is created using the dNEAT algorithm, which is an evolutionary algorithm...

A large-scale benchmark for evaluating the brain-likeness of neural networks.

A shallow recurrent model that follows neuroanatomy more closely than standard machine learning ANNs, and is among the top models on Brain-Score yet remains competitive on...

The dataset used in the paper for cinematic motion transfer, consisting of NeRF representations of 3D scenes and reference video clips.

Radar signal deinterleaving dataset based on semantic segmentation with neural network

The dataset used in this paper is a synthetic dataset created for the performance versus complexity study of neural network equalizers in coherent optical systems.

The dataset is used to test the proposed tree-structured recurrent switching linear dynamical systems (TrSLDS) model.

The dataset is used to test the proposed tree-structured recurrent switching linear dynamical systems (TrSLDS) model.

The dataset is used to study the size and width of autoencoders consisting of Boolean threshold functions.

The BrainScaleS-2 system is used for analog inference acceleration.

Single stream parallelization of recurrent neural networks for low power and fast inference

Training Deep Neural Networks is complicated by the fact that the distribution of each layer's inputs changes during training, as the parameters of the previous layers change.

The dataset used in this paper is a convolutional neural network with Power-of-Two (PoT) quantisation.

Neural 3D Video Synthesis dataset contains 3D videos synthesized using neural networks.